AI safety and research company Anthropic calls for proposals to evaluate advanced models

Anthropic, an organization that does analysis into AI safety, is looking for proposals on methods to guage superior studying fashions.

The fast development of AI means there are new AI suppliers and fashions on a regular basis. Each major tech company has its own model, whereas there are dozens extra smaller ones as nicely. That implies that the business has a rising benchmarking drawback, making it robust to precisely consider how nicely an AI mannequin performs.

Not solely is it onerous to state how efficient a mannequin is, but it surely’s additionally onerous to guage the dangers concerned with AI security. Anthropic is looking for proposals to plug this hole in AI analysis.

“Growing high-quality, safety-relevant evaluations stays difficult, and the demand is outpacing the provision,” the corporate writes. “To deal with this, at this time we’re introducing a brand new initiative to fund evaluations developed by third-party organizations that may successfully measure superior capabilities in AI fashions.”

The principle focus of the proposals needs to be centered round: AI Security Stage assessments; superior functionality and security metrics; and infrastructure, instruments, and strategies for growing evaluations. There needs to be particulars on exams that may assess an AI mannequin’s capacity to perform duties starting from cyberattacks, engaged on weapons of mass destruction, together with nuclear weapons, and creating deepfakes or misinformation).

The best way to submit a proposal on AI security analysis

You’ll be able to learn extra particulars on every of the sections that Anthropic is looking for proposals on and submit a proposal on the research company’s website. The staff is reviewing submissions on a rolling foundation and can observe up with choose proposals to debate subsequent steps.

Anthropic has allotted numerous ranges of funding to assist get these analysis choices to their subsequent phases, in addition to providing the chance to speak immediately with specialists from throughout their in-house analysis and security groups.

Featured picture: Ideogram